Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
45 Cards in this Set
- Front
- Back
Two types of Stats
|
Inferential, and Descriptive
|
|
Variable
|
Characteristic that can have different values
|
|
Value
|
Possible numbers/categories that a score can have.
|
|
Score
|
Particular persons value on a a variable
|
|
Numeric (Quantitative) Level of Measurement
|
Two types: Equal-Interval and Rank-Order
|
|
Equal-Interval
|
Ratio scale (ex. # of siblings or GPA)
|
|
Rank Order
|
Ordinal variables. Class rank or winner in a race. Order carries magnetude
|
|
Nominal (Categorical) Variable
|
Gender; Nominal; No numerical value
|
|
Discrete Variables
|
Have specific values (Age in years). Cannot have values in between values (No fractions or decimals. All whole numbers/integers)
|
|
Continuous Variables
|
Have infinite number of values between two values
|
|
Moduality
|
The number of modes a data set has
|
|
Unimodal Distributions
|
A data set with only one mode
|
|
Bimodal Distributions
|
A data set with 2+ modes. Are particularly disruptive when measuring central tendency.
|
|
Rectangular Distributions
|
More than one mode, but all pretty evenly dispersed
|
|
Heterogeneous Samples
|
Sample of nonsimilar popular observations. (Example: age of grad school and undergrad students).
|
|
Symmetrical Distribution
|
Have tails on both sides. One mode and is in the middle.
|
|
Positive Skew
|
Tail on the right. Data skewed towards left. Median is lower than the mean.
|
|
Negative Skew
|
Tail on the right. Data majority on the left. Median higher than the mean,
|
|
Normal Distribution
|
Symmetrical and Unimodal frequency distribution
|
|
Kurtotic (Pointy)
|
Most data over one or two values. Slim and tall curve
|
|
Kurtotic (Flat)
|
Data almost evenly split among data. Very round.
|
|
Floor Effect
|
Drastic positive skew; doesn't accurately measure extent of research.
|
|
Ceiling Effect
|
Drastic Negative skew; doesn't accurately measure extent of research.
|
|
Measures of Central Tendency
|
Most "Typical"/Common score. Score best represents the whole distribution. Mean, Median and Mode
|
|
Mode
|
Most frequently occurring number in a distribution. Measure of CT for Nominal variables. Main problem: Can have more than one mode.
|
|
Median
|
Midpoint of Distribution. Separates low 1/2 and high 1/2. Not sensitive to extreme scores and outliers.
|
|
Mean
|
Sum of all scores divided by n. M=Ex/n. Most stable-- all #s included in calculations. Not affected by addition/deletion of scores. Used in many statistical procedures.
|
|
Varience
|
SD2=E(x-m)/n
|
|
Z Score
|
the number of standard deviations a score is above or below the mean of the scores in the distribution. Z=x-m/SD
|
|
Raw Score
|
A regular score before it has been converted to a Z score. Even on different variables can be converted into Z scores and directly compared. X=(Z)(SD)+m
|
|
Correlation
|
Can be thought of as descriptive statistics for the relationship between two variables. Describes relationship between two equal-interval numeric variables.
|
|
Scatter Diagram
|
Graph that shows the pattern of relationships of two variables.
|
|
Linear Correlation
|
Relationship between two variables that shows up on a scatter diagram as dots approximating a straight line.
|
|
Curvilinear Correlation
|
Any association between two variables other than a linear correlation. Relationship between two variables that shows up on a scatter diagram as following a systematic pattern that is not a straight line.
|
|
No Correlation
|
No systematic relationship between two variables.
|
|
Positive Correlation
|
High scores go with High scores; Low scores go with low scores; medium---> medium scores; When graphed, line is up and to the right.
|
|
Negative Correlation
|
High scores with low scores; When graphed, line is down to the right.
|
|
Strength of Correlation
|
How close dots fall to a straight line determines the strength of the correlation
|
|
Best Fit Line
|
f(x)=ax+b
|
|
Correlation Coefficient
|
Pearsons (r) tells general trend of relationship between two variables. + means correlation is positive. - means correlation is negative; Ranges from 0-1. 1, -1 mean variables are perfectly correlated. 0 means no correlation.
|
|
Correlation Coefficient Formula
|
r=E(ZxZy)/n
|
|
Possible Directions of Correlation Coefficient
|
X--> Y -- Less sleep means more stress. Y-->X -- more stress means less sleep. Z--> X+Y -- working longer hours causes both stress and less sleep.
|
|
Statistical significance
|
A correlation is statistically significant if it is unlikely that you could have gotten a correlation as big as you did if in fact there was no relationship between variables. If probability is less than some small degree of probability (5%), the correlation is considered statistically significant.
|
|
Predictor Variable
|
X Variable. Independent Variable.
|
|
Criterion Variable
|
Y Variable. Dependent Variable.
|